Comparison among Voice Activity Detection Methods for Korean Elderly Voice

In the elderly voice, a large amount of noise is generated by physiological changes such as respiration, vocalization, and resonance according to age. So it provides a cause for performance degradation when operating a fusion healthcare device such as voice recognition, synthesis, and analysis software with elderly voice. Therefore, it is necessary to analyze and research the voice of elderly people so that they can operate various healthcare devices with their voices. This study investigated the voice activity detection algorithm for the elderly voice using the existing symmetric higher order differential energy function. And it is confirmed that it has better performance in detection of voice interval in the elderly voice compared with the autocorrelation function and average magnitude difference function method. The voice activity detection proposed in this paper can be applied to the voice interface for the elderly, thereby improving the accessibility of the elderly to the smart device. Furthermore, it is expected that the performance improvement and development of various fusion wearable devices for the elderly will be possible.